mirror of
https://github.com/ai-robots-txt/ai.robots.txt.git
synced 2026-10-07 18:07:00 +02:00
Merge pull request #271 from lyrenth/correct-aiwebindex-metadata
Correct AIWebIndex metadata
This commit is contained in:
commit
d8e26238a7
1 changed files with 5 additions and 5 deletions
10
robots.json
10
robots.json
|
|
@ -42,11 +42,11 @@
|
|||
"description": "Scrapes data for AI systems."
|
||||
},
|
||||
"AIWebIndex": {
|
||||
"operator": "Lyrenth that builds an AI-readable index of web content for AI systems",
|
||||
"respect": "Unclear at this time.",
|
||||
"function": "AI Data Providers",
|
||||
"frequency": "Unclear at this time.",
|
||||
"description": "AIWebIndex is a web crawler operated by Lyrenth that builds an AI-readable index of web content for AI systems. More info can be found at https://knownagents.com/agents/aiwebindex"
|
||||
"operator": "[Lyrenth](https://lyrenth.com)",
|
||||
"respect": "[Yes](https://lyrenth.com/crawler-policy)",
|
||||
"function": "AI Search Crawlers",
|
||||
"frequency": "At most one request per domain every 2 seconds, and slower where robots.txt sets a longer Crawl-delay.",
|
||||
"description": "Builds an index of public pages and serves them to AI agents as extracted, readable text with attribution and a link back to the source. Does not train foundation models on crawled content. Identity can be checked three ways: published IP ranges at https://lyrenth.com/bot/ip-ranges.json, forward-confirmed reverse DNS under lyrenth.com, and Web Bot Auth signatures (RFC 9421). Full policy at https://lyrenth.com/crawler-policy"
|
||||
},
|
||||
"amazon-kendra": {
|
||||
"operator": "Amazon",
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue